NLP from ScratchA hands-on learning path through core NLP concepts
8 notebooks. 3 real datasets. One linear path from raw text to a working classifier. All code is yours to run — no fluff, no black boxes.
The NLP Pipeline
Preprocessing
Tokenization
Stemming
Lemmatization
POS Tagging
Feature Extraction
Word2Vec
Classification
Modules
8 Notebooks
Datasets
IMDB · Friends · GOT
Libraries
NLTK · spaCy · gensim · sklearn